Xentir Claude 3.5 Haiku vs Llama 3.3 70B
Claude 3.5 Haiku · Anthropic, released 2024-10-22
Llama 3.3 70B OPEN WEIGHTS · Meta AI, released 2024-12-06
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
Llama 3.3 70B leads on more of the 4 benchmarks where both are measured — Claude 3.5 Haiku on 1, Llama 3.3 70B on 3. The remaining 5 of 9 tracked benchmarks cannot be compared: 1 has a result for only one of the two models, 4 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 4 of 9 tracked benchmarks for both models — Claude 3.5 Haiku leads on 1, Llama 3.3 70B leads on 3.
| Benchmark | Claude 3.5 Haiku | Llama 3.3 70B | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 127.2 | 127.3 | Llama 3.3 70B |
| SWE-bench Verified | Not measured | Not measured | Not measured on both |
| GPQA Diamond | 0.381 | 0.474 | Llama 3.3 70B |
| MATH Level 5 | 0.464 | 0.416 | Claude 3.5 Haiku |
| OTIS Mock AIME 2024-2025 | 0.043 | 0.051 | Llama 3.3 70B |
| FrontierMath | 0.003 | Not measured | Comparison unavailable — Llama 3.3 70B has no published result |
| FrontierMath Tier 4 | Not measured | Not measured | Not measured on both |
| SimpleQA Verified | Not measured | Not measured | Not measured on both |
| Chess Puzzles | Not measured | Not measured | Not measured on both |
What remains uncertain
- Llama 3.3 70B has no published result on FrontierMath.
- 4 tracked benchmarks have no published result for either model.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.
Full profiles
Claude 3.5 Haiku → · Llama 3.3 70B → · the full AI Model Rankings table